arXiv Machine Learning September 4, 2026 By Frank Hu, Shriram Chennakesavalu, David Graff

Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings

Read the original on arXiv Machine Learning →

Frontier large language models (LLMs) are examined as batch optimizers in both continuous and discrete settings. The study finds that while LLMs perform competitively in zero‑shot optimization of numerical test functions, their performance is less robust than classical non‑LLM methods. However, LLMs excel in semantically rich, discrete spaces that resemble their pretraining data, demonstrating strong batch optimization behavior in such contexts.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Aug 7

Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging

arXiv:2608. 05541v1 Announce Type: new Abstract: Evolution Strategy (ES) is a promising alternative to gradient-based fine-tuning for resource-constrained Large Language Model (LLM) reasoning.

By Yu Gu, Zhi Zheng, Yunpeng Ba, Xialiang Tong, Mingxuan Yuan, Zhenkun Wang

llms fine-tuning

arXiv AI

Jul 2

Predicting LLM Reasoning Performance with Small Proxy Model

arXiv:2509. 21013v4 Announce Type: replace-cross Abstract: Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize datasets before scaling up.

By Woosung Koh, Juyoung Suk, Sungjun Han, Se-Young Yun, Jamin Shin

llms benchmarks safety

arXiv AI

Sep 7

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

The paper surveys efficient reasoning in large language models, contrasting fast intuitive (System 1) and slow deep (System 2) reasoning. It analyzes why System 2 is computationally costly yet more accurate, and why System 1 is efficient but less effective. The survey covers causes of inefficiency, patterns of reasoning behavior, and potential solutions to balance performance and computational budgets, offering actionable insights and an open‑source repository for ongoing research.

By Rui Wang, Hongru Wang, Boyang Xue, Jianhui Pang, Shudong Liu, Yi Chen, Jiahao Qiu, Derek Fai Wong, Heng Ji, Kam-Fai Wong

llms

arXiv AI

Jun 11

GPO: Learning from Critical Steps to Improve LLM Reasoning

arXiv:2509. 16456v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks.

By Jiahao Yu, Zelei Cheng, Xian Wu, Xinyu Xing

llms fine-tuning benchmarks

arXiv AI

Jun 9

Post-training is (Massive) Supervised Learning

arXiv:2606. 07527v1 Announce Type: cross Abstract: The prevailing paradigm for training LLMs has evolved to rely on a massive post-training phase consisting of SFT and RL.

By Michael Hassid, Yossi Adi, Roy Schwartz

llms reinforcement-learning fine-tuning benchmarks

arXiv Computation and Language

Sep 23

ClusterFewshot: Improving Few-shot Optimization for LLMs workflow

ClusterFewshot is a new strategy for selecting few‑shot demonstrations in large language model workflows. It combines semantic structuring with utility‑aware scoring to build representative demonstration sets, improving accuracy over prior bootstrap‑based methods. In DSPy‑based pipelines, it substantially reduces optimization cost across multiple benchmarks while consistently outperforming earlier approaches in both standalone prompt tuning and hybrid prompt‑weight optimization.

By Omri Bar Haim, Shahar Katz, Lior Wolf

llms benchmarks

One email a morning, machine-written

Related stories

Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging

Predicting LLM Reasoning Performance with Small Proxy Model

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

GPO: Learning from Critical Steps to Improve LLM Reasoning

Post-training is (Massive) Supervised Learning

ClusterFewshot: Improving Few-shot Optimization for LLMs workflow